Search Results for "performance" - Page 2
Sort By:
Showing 55 open source projects for "performance"
View related business solutions-
Earn up to 16% annual interest with Nexo.Generate interest, access liquidity without selling, and execute trades seamlessly. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
1
SmallCode
AI coding agent optimized for small LLMs. 87% benchmark
SmallCode is a terminal-native AI coding agent optimized for local models running on consumer hardware. It is designed to extract useful coding performance from smaller LLMs, especially models in the 7B to 20B range. The project focuses on making local coding assistance practical without requiring massive cloud-hosted models for every task. Its workflow is built around terminal usage, which makes it suitable for developers who prefer command-line control and local project context. smallcode emphasizes efficient agent behavior, careful tool use, and benchmark-driven improvements for constrained models. ... -
2
One API
The LLM API management & distribution system
...It acts as a gateway that allows developers to manage and route requests to different large language models and AI services without needing to integrate each provider separately. The system supports multiple backends, enabling users to switch between providers or balance usage based on cost, performance, or availability. It includes features such as authentication, rate limiting, and usage tracking, making it suitable for production environments. One API also provides a web-based dashboard for managing keys, monitoring usage, and configuring routing rules. Its architecture is designed for scalability, allowing teams to deploy it as a centralized layer in their AI infrastructure. ... -
3
Devon
Open source AI pair programmer for coding, debugging, automation
...Devon uses a client-server architecture with a Python backend and multiple user interfaces, including a terminal interface and an Electron-based desktop application. Devon integrates with multiple large language models, allowing users to choose between different providers for performance, cost, and latency considerations. It is capable of performing tasks such as debugging, writing tests, analyzing code structure, and navigating complex repositories. Devon also includes features for session management, enabling users to start, pause, and revert actions while maintaining context. -
4
browserable
Open source and self-hostable browser automation library for AI agents
Browserable is an open-source browser automation framework designed specifically for AI agents that need to interact with web interfaces in a human-like way. The project provides tools that allow automated agents to navigate websites, click buttons, fill out forms, and extract information from pages without manual scripting of each step. Built primarily in JavaScript, the framework offers both a developer-friendly SDK and a REST API that allow integration with AI applications and automation... -
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
5
rep+
Burp-style HTTP Repeater for Chrome DevTools with built‑in AI
...Additional productivity features like exporting/importing requests, various representation modes (pretty/raw/hex), and bulk replay mechanisms make it suitable for debugging, performance checking, or security probing. -
6
Pro Workflow
Claude Code learns from your corrections: self-correcting memory
...The framework includes a collection of prebuilt skills and workflows that have been tested in real-world scenarios, providing a strong starting point for developers. It emphasizes continuous improvement, where each interaction contributes to better performance in future tasks. The system also integrates agent teams, allowing complex workflows to be distributed across specialized components. Overall, Pro-workflow transforms AI-assisted coding into an adaptive and evolving process that improves with use. -
7
OpenMemory
Local long-term memory engine for AI apps with persistent storage
OpenMemory is a self-hosted memory engine designed to provide long-term, persistent storage for AI and LLM-powered applications. It enables developers to give otherwise stateless models a structured memory layer that can store, retrieve, and manage contextual information over time. OpenMemory is built around a hierarchical memory architecture that organizes data into semantic sectors and connects them through a graph-based structure for efficient retrieval. It supports multiple embedding... -
8
Preswald
Python tool for browser-based interactive data apps in one file
...Preswald emphasizes a code-first workflow where users define applications entirely in Python while using built-in UI components such as tables, charts, and forms. It also includes a reactive execution model that only recomputes necessary parts of the app, improving performance and responsiveness. -
9
David UI
Free Tailwind CSS UI component library for modern web interfaces
...It supports both simple module imports and more advanced programmatic usage with TypeScript, giving developers greater control over component behavior and configuration. It emphasizes developer experience, performance, and maintainability. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
Code2Prompt
Convert codebases into structured prompts optimized for LLM analysis
...This approach helps developers quickly provide full project context to AI models without manually copying files or assembling prompts. code2prompt is built in Rust and focuses on performance, enabling fast traversal of large repositories while maintaining low resource usage. It also respects common project conventions such as .gitignore, ensuring that unnecessary files are automatically excluded from the generated prompt. The generated output can be saved to a file, printed to standard output, or copied to the clipboard for immediate use. ... -
11
MCP Toolbox for Databases
Open source MCP server that exposes database tools for AI agents
...It provides a central service that exposes database operations as reusable tools that can be consumed by AI agents and developer workflows. It handles common infrastructure concerns such as authentication, connection pooling, and performance optimization so developers do not have to implement them individually in each application. By defining tools and data sources through configuration files, developers can standardize how AI systems access and operate on database resources. GenAI Toolbox is designed to integrate with agent frameworks and development environments so that AI assistants can execute database-related tasks with proper context and security. ... -
12
Flow Teleprompter
A Windows first teleprompter with voice tracking and AI drafting.
...It also includes an invisible always-on-top overlay for Screenshare bypass, remote script delivery via quick-connect QR links, and optional Groq-powered AI drafting. Flow keeps RAM usage minimal while maintaining top-tier performance and staying completely out of your way. -
13
PC Workman HCK
AI-powered PC monitoring that explains. Not shows numbers/spikes.
Your PC says CPU 87%. PC Workman says why, since when, and what to do about it. Real-time system monitor with built-in offline AI. No cloud. Your data stays on your machine. What's inside: -hck_GPT: 82-intent AI assistant. -Ask it anything about your PC in Polish or English. -9-layer routing, learns your usage patterns over weeks. -TURBO mode: one click stops unnecessary services (Gaming/Work/Economy profiles), switches power plan, flushes RAM, freezes idle apps. -One click restores... -
14
HasMCP
Convert API into MCP Server in seconds
...For robust security, it includes Secure Secret & Gateway Management to safeguard sensitive credentials in an encrypted vault. MCP Composition enables the construction of high-performance, modular AI systems. Finally, comprehensive Observability & Telemetry tools offer deep insights into tool usages. -
15
GNNPCSAFT Web App
Smart Thermodynamic Modeling with Graph Neural Networks
The GNNPCSAFT Web App is an implementation of our project that focuses on using Graph Neural Networks (GNN) to estimate the pure-component parameters of the Equation of State PC-SAFT. We developed this app so the scientific community can access the model's results easily. In this app, the estimated pure-component parameters can be used to calculate thermodynamic properties and compare them with experimental data from the ThermoML Archive. More info on github repository. -
16
GNNPCSAFT Chat
Chatbot with GNNPCSAFT
...In this app, you can chat with LLM models (Gemini or Ollama) with GNNPCSAFT tools, allowing you to ask questions about the PC-SAFT parameters of various compounds, predict thermodynamic properties, and get insights into the GNNPCSAFT's performance. -
17
SuperAGI
A dev-first open source autonomous AI agent framework
...Join a community of developers constantly contributing to make SuperAGI better. Access your agents through a graphical user interface. Interact with agents by giving them input, permissions, etc. Agents typically learn and improve their performance over time with feedback loops. Run multiple agents simultaneously to improve efficiency and productivity. Connect to multiple Vector DBs to enhance your agent’s performance. Each agent is unique, use different models of your choice. Get insights into your agent’s performance and optimize accordingly. Control token usage to manage costs effectively. ... -
18
pipeless
A computer vision framework to create and deploy apps in minutes
...You can easily use industry-standard models, such as YOLO, or load your custom model in one of the supported inference runtimes. Pipeless ships some of the most popular inference runtimes, such as the ONNX Runtime, allowing you to run inference with high performance on CPU or GPU out-of-the-box. You can deploy your Pipeless application with a single command to edge and IoT devices or the cloud. -
19
Chunsong Customer Service
An intelligent customer service system
CSKeFu is a Customer Support System for Enterprises in a high-performance Low-Touch way, open source and free for the world by Chatopera. At Chatopera, we believe that the more you focus on customer service, the better your business/the more you care about your customers, the better income you earn in return. Help enterprises quickly get out-of-the-box free intelligent customer service system to get a customer support system in minutes. -
20
gpu_poor
Calculate token/s & GPU memory requirement for any LLM
gpu_poor is an open-source tool designed to help developers determine whether their hardware is capable of running a specific large language model and to estimate the performance they can expect from it. The project focuses on calculating GPU memory requirements and predicted inference speed for different models, hardware configurations, and quantization strategies. By analyzing factors such as model size, context length, batch size, and GPU specifications, the system estimates how much VRAM will be required and how fast tokens can be generated during inference. ... -
21
fe4ml-zh
Feature Engineering for Machine Learning
fe4ml-zh is an open-source project that provides a Chinese translation and structured documentation of the book Feature Engineering for Machine Learning. The repository aims to make advanced feature engineering concepts accessible to a broader audience by translating the content and organizing it into readable documentation and code examples. Feature engineering is a critical component of machine learning pipelines because it determines how raw data is transformed into features that... -
22
Coframe
Coframe brings your UX to life with AI-powered optimization
...Coframe brings the content of your app or website to life through AI-powered optimization, personalization, and overall self-improvement. It takes minutes to integrate, and the ROI is clear to measure. Your website or app gains self-enhancing abilities with Coframe, learning from real-world performance. It's A/B testing, but with a serious upgrade. Coframe uses the latest in AI to generate copy that is tailored to your users. Resulting performance data is fed back in to continuously improve your platform's content. With Coframe, your website or app works for you 24/7, not the other way around. All it takes to get up and running is a few lines of code. ... -
23
MITRE Annotation Toolkit
A toolkit for managing and manipulating text annotations
...It can be customized for specific tasks (e.g., named entity identification, de-identification of medical records). The goal of MAT is not to help you configure your training engine (in the default case, the Carafe CRF system) to achieve the best possible performance on your data. MAT is for "everything else": all the tools you end up wishing you had. -
24
Semantic Segmentation Editor
Web labeling tool for bitmap images and point clouds
A web-based labeling tool for creating AI training data sets (2D and 3D). The tool has been developed in the context of autonomous driving research. It supports images (.jpg or .png) and point clouds (.pcd). It is a Meteor app developed with React, Paper.js, and three.js. -
25
Supervised Reptile
Code for the paper "On First-Order Meta-Learning Algorithms"
...Because Reptile is a first-order algorithm, it avoids computing second derivatives or full meta-gradients, making it computationally simpler while retaining good performance. The repo includes training scripts, dataset fetchers (Omniglot, Mini-ImageNet), and modules for defining the Reptile update logic, variables, and hyperparameters.
